© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 41-GEMMASCOPE-2-RES-65K
    7. 13128
    Prev
    Next
    INDEX
    Explanations

    diverse or code elements

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_41_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    曳
    0.55
     मोड
    0.55
     Nawab
    0.52
    üğ
    0.51
    बाग
    0.51
     ngôn
    0.50
     mại
    0.49
    የር
    0.49
     andDevice
    0.49
    czaj
    0.49
    POSITIVE LOGITS
    надцати
    0.59
    ٢
    0.57
     Resolve
    0.55
    答案
    0.55
    ૨
    0.53
     ٢
    0.53
    ressant
    0.51
    オ
    0.51
    萂
    0.51
     ۸
    0.50
    Activations Density 0.000%

    No Known Activations